BUSINESS RESEARCH

METHODS
January 15, 1010

SUBMITTED BY:

GROUP 11- SECTION -E

ASHRITHA (Seat No. 52)

PRIYA KABRA (Seat No.54)

SAAKSHI HARSH (Seat No.56)

TARUN ARORA (Seat No.58)

RISHAB JAIN (Seat No.60)

SUBMITTED TO: Prof. SUSHAMA MARATHE

 TABLE OF CONTENTS

1. Research Problem…………………...………………………………………4
2. Purpose of study………………………..…………………………………….5
3. Survey conducted………….……………………………………………. ….5
4. Variables..…………………………………………………………………….… 6
5. Codes……………..……………………………………………………………….7
6. Analysis………………………………………………………………………….10
7. Factor Analysis……………….………………………………………………11
8. Discriminant Analysis………………………………………….………….19
9. Cluster Analysis …………………………………………………………….23
10. Recommendations…………………………………………………24
11. Conclusion…………………………………………………………….24

2|Page
 ACKNOWLEDGEMENT
A project is never the work of an individual. It is moreover a combination of ideas,
suggestions, reviews, contributions and work involving many people. It cannot be completed
without guidelines. It is a pleasure to acknowledge gratefully to all those people who helped us a
lot in the creation of this project and shared their experiences. We would like to express our
sincere indebtedness to Dr. S. Marathe (Professor of Business Research Methodology, IBS
Hyderabad) for giving us the opportunity to work on this project and make it a success. Her
constant guidance and suggestions paved way for the completion of this project. We would also
like to thank all those people who spared time to fill our questionnaires.

Ashritha Rao (09BSHYD0557)

Priya Kabra (09BSHYD0593)

Rishab Jain (09BSHYD0666)

Saakshi Harsh (09BSHYD0707)

Tarun Arora (09BSHYD0921)

3|Page
RESEARCH PROBLEM: How The Buying Behavior Of Indian Youth Influences Organized
Retail?

PURPOSE OF STUDY:

As India continues on its growth path, the retail sector in the country is bound to come across
with opportunities never seen before. Till a few years back, India had more of an unorganized
retail sector, with small vendors occupying a major share of the industry.

But, today the business scenario is changing. This sector, namely the unorganized sector is
moving towards what we call as organized retail sector.

The Indian organized retail industry is valued at about $400 billion presently and is expected to
reach $637 billion by 1015.

The Indian market has become a very lucrative and attractive market for retail investment from
all around the world. Various factors have contributed towards the growth of organized retail
sector in India. Some of these are:

- Increase in the purchasing and spending power of Indians

- Rapid urbanization

- Increase in the number of working women

- Large number of working young population

Here we propose to look at how the last factor, i.e., the large young population of the country,
and its buying behavior is helping in the growth of the Indian retail sector.

Through a survey, we tend to find out how many people are actually fulfilling their various needs
by purchasing goods from the organized retail outlets. Is it having a considerable impact on the
sales of the sector? What will be the future of these retail outlets? Will they be able to survive in
the increasing competition?

4|Page
Hence, the key objective of this paper is to uncover the motives that drive young people to shop
in these organized retail outlets, so that it helps the retailers to understand the customer
perception, attitude and buying behavior and utilize the same to get a big chunk of the retail
industry.

Survey Conducted:

The organizations we are focusing on are Shoppers stop, Lifestyle, Globus, Max. Apart form this
the respondent is also given a choice to write the name of any other such organized retail outlet
that he visits. This question shall help us uncover the most popular retail outlets that are visited
by the youth of the country.

Age Group: The questionnaire is being responded by people within an age group of 15-30 years
which includes mainly the students and also some working professionals and businessmen.

Sample Size: We plan to take a sample size of 150 people, mainly those who are students at
IBS, Hyderabad.

Pre-testing refers to the testing of the questionnaire on a small sample of respondents selected
on a convenient basis that is not too divergent from the actual respondents. Also it helps us to
revise the questionnaire by identifying flaws and eliminating any ambiguous questions. For this
purpose, we conducted a pre test with a sample of 30 respondent and checked our questionnaire
for reliability and validity. The test conducted test was successful.

Multiple choice questions that cover the major buying decisions of the consumer have been
taken in the questionnaire. All the questions are closed ended questions.

The respondent is required to select the option that best describes their opinion. In case a
respondent looks at two factors mentioned in the same question, he/she is required to select the
option that influences his buying decision the most.

Through the various questions, we are trying to find out what is the main factor affecting:

- Purchase from an organized retail store

- Why a buyer goes to an organized retail store

5|Page
 - What attracts him to buy from an organized retail store
- What are the factors that influence a buyers mind when he/she selects an outlet
- Do advertisements influence the buying behavior?
- Does the social circle of the youth affects his/her buying decision
- What effect does this have in the sale of the retail outlets

Variables considered:
As regards the various questions, the following are the variables being taken for analysis for
each question:

Which is the retail outlet you prefer the most :- Preference

How often do you visit a retail outlet:- Frequency

What is the basis of your purchases:- Basis

What attracts you to buy from an organized retail outlet:- Attractor

I enjoy shopping as it is also a meeting place with friends: - Enjoyment

I always compare prices before selecting the best offer:- Market study

I always do not need a purpose to buy :- Motive

I choose products which people in my status group buy:- Societal efffect

Advertisements influence my shopping behavior:- Advertisments

I select a particular outlet to shop if the friends/colleagues are doing the same:- Referrals

I go out to shop as it helps me decreasing my depression:- Reduces depression

I go out to shop because it is my hobby:- Passion

I cannot shop at a noisy place:- Ambiance

6|Page
Codes:
The following codes have been assigned to the various questions:

[Link]:

Male- (1) Female- (2)

Q3. What is your occupation?

Student – (3) Professional –(4) Businessman-(5) Any other(6)

Q4. What is your annual family income?

Less than Rs.3 lakhs- (7) Rs.3lakhs – Rs. 5 lakhs-(8) More than Rs.5 lakhs- (8)

Q5. Which is the retail outlet you prefer the most?

Lifestyle-(10) Shoppers stop-(11) Globus- (12) Max - (13) Others—(14)

Q6. How often do you visit a retail outlet?

More than once a week – (15) Once a week –(15) Once a fortnight- (15) Once a month-(16)

Q7. What is the basis of your purchases?

Brand –(17) Price- (18) Quality- (19)

Q8. What attracts you to buy from an organized retail outlet? Availability of various brands
under one roof-(20) Offers and schemes – (21) Wide range of Products-(22) Accessibility-(23)

[Link] Question Strongly Agree Can’ Disagree Strong

. agree t say Disagree

7|Page
 1. I enjoy shopping as it is also a meeting 101 102 103 104 105
place with friends.

2 I always compare prices before selecting 101 102 103 104 105
the best offer.

3 I always do not need a purpose to buy. 101 101 103 104 105

4 I choose products which people in my 101 102 103 104 105

status group buy.
5 Advertisements influence my shopping 101 102 103 104 105
behavior

I select a particular outlet to shop if the 101 102 103 104 105
6 friends/colleagues are doing the same.

7 I go out to shop as it helps me decreasing 101 102 103 104 105

my depression.
8 I go out to shop because it is my hobby. 101 102 103 104 105

9 I cannot shop at a noisy place. 101 102 103 104 105

8|Page
The survey was filled by a varied population. All the respondents contacted came out to be those
who frequently visit malls. None of the respondents had filled Never as an option when asked
the frequency of their visit to malls. Taking the sample as a representation of the whole
population, it can be said that the youth does form a major part of the customer base of these
retail outlets. They form a major source of their earnings. With the youth depending quite a bit
on these organized retail outlets, the future of these organizations seems to be bright. To analyse
the main factors affecting the buying behaviors of this large customer base, the research has been
conducted.

9|Page
ANALYSIS:

To analyze the data, various tools from SPSS have been used :

-Factor Analysis

-Discriminant Analysis

-Cluster Analysis

10 | P a g e
Factor Analysis:

Factor analysis is a data reduction technique it reduces the attribute space from a larger number
of variables to a smaller number of factors and as such is a "non-dependent" procedure.

Here we have various questions to judge the reason for people buying at organized retail outlets.
So we need to find the factors for these questions.

Procedure:

The analysis in the SPSS can be done as follows:

1) The data is to be imported from the excel file

2) Go to analyze Data Reduction Factor Analysis
3) Select the variables to be analyzed
4) In descriptive we select the anti-image and KMO and Bartlett test options are to be
checked.
5) In the extraction option select the scree plot and check the Eigen value is greater than 1
6) In options select the varimax rotation and click ok

Analysis:

KMO and Bartlett's Test

Kaiser-Meyer-Olkin Measure of Sampling Adequacy. .776

Bartlett's Test of Sphericity Approx. Chi-Square 277.046

df 36

Sig. .000

11 | P a g e
KMO Test:

The KMO test tells that it is appropriate to apply factor analysis test for the following
data or not. The value of KMO if is greater than 0.5 than we can move with factor
analysis

Here we have KMO=0.776 so factor analysis can be applied here

Bartlett Test:

The Bartlett Test tells that it is appropriate to apply factor analysis test for the following
data or not. The P value, if is less than 0.001 than only the analysis can be done. Here as
the value of the test is less than 0.01 we can apply factor analysis.

Communalities:

Communality, h2, is the squared multiple correlation for the variable as dependent using the
factors as predictors. The communality measures the percent of variance in a given variable
explained by all the factors jointly and may be interpreted as the reliability of the indicator

Low communality. When an indicator variable has a low communality, the factor model is not
working well for that indicator and possibly it should be removed from the model.

The communality is mainly greater than 0.5 than it can be said that it is contributing. Here the
variable other than the customer services facilities is significant so we can remove the Motive
variable from the model.

12 | P a g e
 Communalities

Initial Extraction

Enjoyment 1.000 .644

Market Study 1.000 .718

Motive 1.000 .347

Societal Effect 1.000 .622

Advertisments 1.000 .620

Referrals 1.000 .645

Reduces Depression 1.000 .617

Passion 1.000 .593

Ambiance 1.000 .556

Extraction Method: Principal Component Analysis.

Total Variance Explained:

This table shows that the factors greater than value 1 are taken and other are discarded for the
factors

Here seeing first three factors have the Eigen value greater than 1 so are taken as a factors

13 | P a g e
 Total Variance Explained

Extraction Sums of Squared

Initial Eigenvalues Loadings Rotation Sums of Squared Loadings

Compon % of Cumulative % of % of Cumulativ

ent Total Variance % Total Variance Cumulative % Total Variance e%

1 3.075 34.168 34.168 3.075 34.168 34.168 2.200 24.442 24.442

2 1.281 14.235 48.403 1.281 14.235 48.403 2.127 23.632 48.074

3 1.004 11.158 59.561 1.004 11.158 59.561 1.034 11.487 59.561

4 .917 10.185 69.746

5 .754 8.382 78.129

6 .663 7.372 85.501

7 .470 5.217 90.717

8 .440 4.885 95.602

9 .396 4.398 100.000

Extraction Method: Principal Component

Analysis.

Extraction:

The factors that are taken according their Eigen values are taken by extraction in the table

Here seeing the values after the extraction the variance is not distributed equally the variance of
the 1st factor is comparatively more so we need to rotate.

Rotation:

Rotation has the effect of optimizing the factor structure and one consequence for this data is that
the relative importance of all the three factors is equalized

14 | P a g e
Scree Plot

The scree plot is mainly drawn for Eigen value V/s Component Number

It shows the number of variable that has been taken as factors. Whichever has values greater
than 1 are taken

15 | P a g e
Component Matrix

The component matrix shows the contribution of variables in the factors so it helps to segregate
the variables according the factors. This matrix shows the values before rotation

The Components has the values as follows:

a) Factor1-Enjoyment, Motive, Societal Effect, Advertisments, Referrals, Reduces

Depression, Passion
b) Factor2- None
c) Factor3-Market Study

Component Matrixa

Component

1 2 3

Enjoyment .693 -.297 .274

Market Study .097 .500 .677

Motive .514 -.288 .006

Societal Effect .698 .358 -.077

Advertisments .690 .379 -.024

Referrals .644 .462 -.130

Reduces Depression .673 -.402 .053

Passion .614 -.445 .130

Ambiance .336 .121 -.654

Extraction Method: Principal Component Analysis.

a. 3 components extracted.

Rotated Component Matrix

The varimax method is used here for rotation, It is performs a orthogonal rotation

16 | P a g e
Varimax rotation is an orthogonal rotation of the factor axes to maximize the variance of the
squared loadings of a factor (column) on all the variables (rows) in a factor matrix, which has the
effect of differentiating the original variables by extracted factor. Each factor will tend to have
either large or small loadings of any particular variable. A varimax solution yields results which
make it as easy as possible to identify

The Components after rotation has the values as follows:

a) Factor1- Enjoyment, Motive, Reduces Depression, Passion

b) Factor2- Societal Effect, Advertisments, Referrals,
c) Factor3- Market Study
d) Factor4- Ambiance

17 | P a g e
Rotated Component Matrixa

Component

1 2 3

Enjoyment .759 .218 .142

Market Study -.092 .279 .795

Motive .559 .155 -.103

Societal Effect .253 .747 .013

Advertisments .246 .744 .070

Referrals .134 .792 -.004

Reduces Depression .759 .175 -.100

Passion .764 .089 -.037

Ambiance .006 .448 -.596

Extraction Method: Principal Component Analysis.

Rotation Method: Varimax with Kaiser Normalization.

a. Rotation converged in 5 iterations.

18 | P a g e
Discriminant Analysis

Objectives:

1. Development of discriminant function (linear combination of the predictor variables),

which will best discriminate between the categories of the criterion variables.
2. Examining whether significant differences exist among the groups, in terms of the
predictor variable.
3. Determining which predictor variable contributes the most to the inter-group differences.
4. Classifying the cases to one of the groups, based on the values of the predictor variables.
5. Evaluating the accuracy of the classification.

To undertake Discriminant analysis, the following have been taken as the dependent and the
independent variables:

Dependent Variables: FREQUENCY OF VISIT TO THE ORGANISED RETAIL

Independent Variables: INCOME

PREFERENCE

BASIS

ATTRACTOR

Discriminant function: A variate of the independent variables selected for their discriminatory
power used in the prediction of group membership. The predicted value of the discriminant
function is the discriminant Z score, which is calculated for each object in the analysis.

Z = b0 + b1 X1 + b2 X2 + ………….+ bk Xk

Z = Discriminant Score

bi = discriminant coefficient; i varies from 1 to k

19 | P a g e
 Xi = predictors/independent variables; i varies from 1 to k

Canonical
Discriminant Function
Coefficients
Function
1
Income -.683
Preference .301
Basis .389
Attractor .721
(Constant) -19.896
Unstandardized
coefficients

Here , we have the following discriminant function:

Z=-19.896 - 0.683X1 + 0.301X2 + .389X3 + .721X4

Discriminant score (Z): It is a score defined by the discriminant function for each object in the
analysis and usually stated in the standardized terms. Also referred to as the Z score, it is
calculated for each object on each discriminant function. It is used in conjunction with the
cutting score to determine the predicted group membership.

Discriminant loadings: Measurement of simple linear correlation between each independent

variable and the discriminant (Z) score for each discriminant function. Discriminant loadings are
calculated whether or not an independent variable is included in the discriminant function.

20 | P a g e
Log determinants: Log determinants are a measure of the variability of the groups. Larger log
determinants correspond to more variable groups. Large differences in the log determinants
indicate groups that have different covariant matrices.

Log Determinants
Log
Frequency Rank Determinant
15 4 -.877
16 4 -.582
Pooled within-
4 -.687
groups
The ranks and natural logarithms of
determinants printed are those of the group
covariance matrices.

Here the log determinants are – 0.877 and -0.582

Wilk’s lambda: Wilk’s Lambda, for each predictor, is the ratio of the within group sum of
squares to the total sum of squares.

Its value varies between 0 and 1. Large values (closer to 1) indicate that group means do not
seem to be different. The small values (closer to 0) indicate that group means are different.

Each test displays the result of one way ANOVA for the independent variable using the grouping
variable as the factor. If the significance value is greater than 0.5, the variable probably does not
contribute to the model.

21 | P a g e
 Wilks' Lambda

Test
of
Functi Wilks'
on(s) Lambda Chi-square df Sig.
1 .957 6.478 4 .166

According to the result in the table, every variable in our discriminant model is significant as the
value is less than 0.5. Wilk’s Lambda is another measure of a variable’s potential. Smaller values
indicate the variable is better at discriminating between groups as we see from the output .

Standardized canonical discriminant function coefficients: The standardized coefficient

allows you to compare variables measured on different scales. Coefficients with large absolute
values correspond to variables with greater discriminating ability.

Standardized Canonical
Discriminant Function
Coefficients

Function

Income -.486

Preference .364

Basis .335

Attractor .711

Here , in the output , the variable attractor , has the highest coefficient of 0.711

22 | P a g e
CLUSTER ANALYSIS
Using Cluster analysis, a group of the similar respondents is formed, in contrast to the factor
analysis where a group of the related variables is formed.

Cluster analysis has three different procedures which can be used to cluster data: Hierarchical
cluster analysis, k-means cluster and two step cluster.

Hierarchical cluster is the most straight forward clustering method.

Here, on running the Cluster analysis we can see, from the table, and the dendogram, that
there are four clusters being formed.

23 | P a g e
Recommendations:
1) Youth have a motive to enjoy the shopping experience. They take it as an outing, for fun,
as well.
2) The youth of the country take in to consideration their peer groups recommendations
when going out to shop
3) Youth in the country are price sensitive as well.
4) Moreover, Advertisements do have a major impact on the buying behavior of the youth.

Conclusion
Youth are an important consuming class owing their disposable incomes. This chunk,
which forms a major part of their customer base is affected by various factors at the time of
purchasing.

Some of the factors are not in the control of the businesses, like, the recommendations of
the people around them. Other factors such as advertisements, do have an impact on the
consumers mind. These factors, which are having a direct impact on the consumer, should not at
all be ignored by the organizations.

The buying behavior of the consumers can group the customers in to various groups,
depending to which the organizations can target each of these groups, with different strategies.

The tastes and preferences, income level also have an impact on the number of times the
a consumer visits these retail outlets. These factors, though not in direct control of the business,
should be looked at and addressed to with providing a wide range of services, that can fulfill the
demands of the people at large.

24 | P a g e